This scaffolds the initial directory structure for a Recoup sandbox by fetching organizations and artists via the CLI and creating a workspace folder for each one. It's meant to run once, right after a sandbox is created and before any work begins. The skill checks for an existing orgs/ directory first so you don't duplicate things, then creates artist folders using the exact slug from the API and drops a RECOUP.md marker file in each one with the artist's name, slug, and UUID. That marker is what ties the workspace back to the platform. It handles both personal and org API keys by conditionally passing the account flag. One less manual setup step when spinning up new environments.

skills.sh installs
1.6K
last updated
Jul 14, 2026

Install

$ npx -y skills add recoupable/setup-sandbox --skill setup-sandbox --agent claude-code

Installs into .claude/skills of the current project.

Files

Setup Sandbox

Create the folder structure for the connected account's organizations and artists.

Environment

  • RECOUP_ACCOUNT_ID — The account ID to fetch data for. Only needed when using an Org API Key. When using a Personal API Key, omit the --account flag and the CLI will use the authenticated account automatically.

Steps

Sponsors

Details

Repository
github.com/recoupable/setup-sandbox
Category
DevOps & CI/CD
1nvidia avatartao-run-on-local-dockernvidia/skillsLocal or remote Docker execution for TAO SDK job containers using a Docker daemon with NVIDIA GPU runtime. Use when running TAO jobs on the current machine, a d1.6Kskills.sh installs
2nvidia avatartao-run-automl-deft-pipelinenvidia/skillsRun the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 1.6Kskills.sh installs
3buildgreatproducts avatarbuild-loop-codexbuildgreatproducts/builder-osUse when building features with **Codex** (OpenAI Codex CLI) in any codebase and the work should go through a disciplined build → review → test → fix loop. Trig1.5Kskills.sh installs
4aradotso avatarharvard-art-museum-data-pipelinearadotso/data-skillsharvard art museum data pipeline1.5Kskills.sh installs
5aradotso avatarharvard-artifacts-data-engineering-pipelinearadotso/data-skillsharvard artifacts data engineering pipeline1.5Kskills.sh installs
6buildgreatproducts avatarbuild-loop-cursorbuildgreatproducts/builder-osUse when building features with **Cursor** in any codebase and the work should go through a disciplined build → review → test → fix loop. Triggers on "run the b1.5Kskills.sh installs